Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Обновлено 2024-10-30 05:49:43 +03:00
Tutel MoE: An Optimized Mixture-of-Experts Implementation
Обновлено 2024-10-28 06:23:06 +03:00
This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluating specific PII recognizers or PII detection models.
Обновлено 2024-10-27 15:51:02 +03:00
Hierarchical Transformers for Knowledge Graph Embeddings (EMNLP 2021)
Обновлено 2024-07-25 14:00:19 +03:00
Code to reproduce experiments in the paper "Constrained Language Models Yield Few-Shot Semantic Parsers" (EMNLP 2021).
Обновлено 2024-05-31 20:48:22 +03:00
A benchmark for code-switched NLP, ACL 2020
Обновлено 2024-05-23 20:25:01 +03:00
This repository contains code and datasets related to entity/knowledge papers from the VERT (Versatile Entity Recognition & disambiguation Toolkit) project, by the Knowledge Computing group at Microsoft Research Asia (MSRA).
Обновлено 2024-03-16 09:53:11 +03:00
Self-training with Weak Supervision (NAACL 2021)
Обновлено 2023-07-25 01:35:52 +03:00
Source code for EMNLP2019 paper "Leveraging Adjective-Noun Phrasing Knowledge for Comparison Relation Prediction in Text-to-SQL".
Обновлено 2023-07-22 19:54:50 +03:00
The code of EMNLP 2019 paper "A Split-and-Recombine Approach for Follow-up Query Analysis"
Обновлено 2023-07-20 15:42:43 +03:00
Scripts to parse arxiv documents for NLP tasks
Обновлено 2023-06-12 22:03:00 +03:00
AI Assistant for Building Reliable, High-performing and Fair Multilingual NLP Systems
Обновлено 2022-08-19 10:21:28 +03:00
A relation-aware semantic parsing model from English to SQL
Обновлено 2021-06-19 03:42:00 +03:00
ReconNER, Debug annotated Named Entity Recognition (NER) data for inconsistencies and get insights on improving the quality of your data.
Обновлено 2020-07-26 11:17:21 +03:00
Code to model Comment-Edit associations in Wikipedia revision histories, based on Zhang et al. (EMNLP 2019)
Обновлено 2019-08-27 03:53:12 +03:00